© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77915
    Prev
    Next
    INDEX
    Explanations

    plus/minus standard deviation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.90
    IBOutlet
    -0.82
     صوتيه
    -0.81
    $'
    -0.76
     Rigidbody
    -0.73
    脚注の使い方
    -0.71
    }$​
    -0.70
    endphp
    -0.69
    MessageTagHelper
    -0.68
    ՚
    -0.68
    POSITIVE LOGITS
     X
    0.56
     alpha
    0.54
     beta
    0.47
     +/-
    0.47
     micro
    0.47
     x
    0.47
     mum
    0.47
    alpha
    0.44
    delta
    0.43
     delta
    0.43
    Activations Density 0.007%

    No Known Activations